ankusa 0.0.8 → 0.0.9
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/README.rdoc +2 -1
- data/Rakefile +4 -26
- data/lib/ankusa.rb +1 -0
- data/lib/ankusa/classifier.rb +3 -0
- data/lib/ankusa/naive_bayes.rb +8 -4
- data/lib/ankusa/version.rb +3 -0
- metadata +6 -33
- data/docs/classes/Ankusa.html +0 -182
- data/docs/classes/Ankusa/CassandraStorage.html +0 -615
- data/docs/classes/Ankusa/Classifier.html +0 -315
- data/docs/classes/Ankusa/FileSystemStorage.html +0 -272
- data/docs/classes/Ankusa/HBaseStorage.html +0 -594
- data/docs/classes/Ankusa/KLDivergenceClassifier.html +0 -194
- data/docs/classes/Ankusa/MemoryStorage.html +0 -467
- data/docs/classes/Ankusa/NaiveBayesClassifier.html +0 -231
- data/docs/classes/Ankusa/TextHash.html +0 -275
- data/docs/classes/String.html +0 -172
- data/docs/created.rid +0 -1
- data/docs/files/README_rdoc.html +0 -294
- data/docs/files/lib/ankusa/cassandra_storage_rb.html +0 -108
- data/docs/files/lib/ankusa/classifier_rb.html +0 -101
- data/docs/files/lib/ankusa/extensions_rb.html +0 -108
- data/docs/files/lib/ankusa/file_system_storage_rb.html +0 -108
- data/docs/files/lib/ankusa/hasher_rb.html +0 -109
- data/docs/files/lib/ankusa/hbase_storage_rb.html +0 -108
- data/docs/files/lib/ankusa/kl_divergence_rb.html +0 -101
- data/docs/files/lib/ankusa/memory_storage_rb.html +0 -101
- data/docs/files/lib/ankusa/naive_bayes_rb.html +0 -101
- data/docs/files/lib/ankusa/stopwords_rb.html +0 -101
- data/docs/files/lib/ankusa_rb.html +0 -112
- data/docs/fr_class_index.html +0 -36
- data/docs/fr_file_index.html +0 -38
- data/docs/fr_method_index.html +0 -95
- data/docs/index.html +0 -24
- data/docs/rdoc-style.css +0 -208
@@ -1,231 +0,0 @@
|
|
1
|
-
<?xml version="1.0" encoding="iso-8859-1"?>
|
2
|
-
<!DOCTYPE html
|
3
|
-
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
|
4
|
-
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
|
5
|
-
|
6
|
-
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
7
|
-
<head>
|
8
|
-
<title>Class: Ankusa::NaiveBayesClassifier</title>
|
9
|
-
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
|
10
|
-
<meta http-equiv="Content-Script-Type" content="text/javascript" />
|
11
|
-
<link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
|
12
|
-
<script type="text/javascript">
|
13
|
-
// <![CDATA[
|
14
|
-
|
15
|
-
function popupCode( url ) {
|
16
|
-
window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
|
17
|
-
}
|
18
|
-
|
19
|
-
function toggleCode( id ) {
|
20
|
-
if ( document.getElementById )
|
21
|
-
elem = document.getElementById( id );
|
22
|
-
else if ( document.all )
|
23
|
-
elem = eval( "document.all." + id );
|
24
|
-
else
|
25
|
-
return false;
|
26
|
-
|
27
|
-
elemStyle = elem.style;
|
28
|
-
|
29
|
-
if ( elemStyle.display != "block" ) {
|
30
|
-
elemStyle.display = "block"
|
31
|
-
} else {
|
32
|
-
elemStyle.display = "none"
|
33
|
-
}
|
34
|
-
|
35
|
-
return true;
|
36
|
-
}
|
37
|
-
|
38
|
-
// Make codeblocks hidden by default
|
39
|
-
document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }</style>" )
|
40
|
-
|
41
|
-
// ]]>
|
42
|
-
</script>
|
43
|
-
|
44
|
-
</head>
|
45
|
-
<body>
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
<div id="classHeader">
|
50
|
-
<table class="header-table">
|
51
|
-
<tr class="top-aligned-row">
|
52
|
-
<td><strong>Class</strong></td>
|
53
|
-
<td class="class-name-in-header">Ankusa::NaiveBayesClassifier</td>
|
54
|
-
</tr>
|
55
|
-
<tr class="top-aligned-row">
|
56
|
-
<td><strong>In:</strong></td>
|
57
|
-
<td>
|
58
|
-
<a href="../../files/lib/ankusa/naive_bayes_rb.html">
|
59
|
-
lib/ankusa/naive_bayes.rb
|
60
|
-
</a>
|
61
|
-
<br />
|
62
|
-
</td>
|
63
|
-
</tr>
|
64
|
-
|
65
|
-
<tr class="top-aligned-row">
|
66
|
-
<td><strong>Parent:</strong></td>
|
67
|
-
<td>
|
68
|
-
Object
|
69
|
-
</td>
|
70
|
-
</tr>
|
71
|
-
</table>
|
72
|
-
</div>
|
73
|
-
<!-- banner header -->
|
74
|
-
|
75
|
-
<div id="bodyContent">
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
<div id="contextContent">
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
</div>
|
84
|
-
|
85
|
-
<div id="method-list">
|
86
|
-
<h3 class="section-bar">Methods</h3>
|
87
|
-
|
88
|
-
<div class="name-list">
|
89
|
-
<a href="#M000025">classifications</a>
|
90
|
-
<a href="#M000024">classify</a>
|
91
|
-
<a href="#M000026">log_likelihoods</a>
|
92
|
-
</div>
|
93
|
-
</div>
|
94
|
-
|
95
|
-
</div>
|
96
|
-
|
97
|
-
|
98
|
-
<!-- if includes -->
|
99
|
-
<div id="includes">
|
100
|
-
<h3 class="section-bar">Included Modules</h3>
|
101
|
-
|
102
|
-
<div id="includes-list">
|
103
|
-
<span class="include-name"><a href="Classifier.html">Classifier</a></span>
|
104
|
-
</div>
|
105
|
-
</div>
|
106
|
-
|
107
|
-
<div id="section">
|
108
|
-
|
109
|
-
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
<!-- if method_list -->
|
117
|
-
<div id="methods">
|
118
|
-
<h3 class="section-bar">Public Instance methods</h3>
|
119
|
-
|
120
|
-
<div id="method-M000025" class="method-detail">
|
121
|
-
<a name="M000025"></a>
|
122
|
-
|
123
|
-
<div class="method-heading">
|
124
|
-
<a href="#M000025" class="method-signature">
|
125
|
-
<span class="method-name">classifications</span><span class="method-args">(text, classnames=nil)</span>
|
126
|
-
</a>
|
127
|
-
</div>
|
128
|
-
|
129
|
-
<div class="method-description">
|
130
|
-
<p>
|
131
|
-
Classes is an array of classes to look at
|
132
|
-
</p>
|
133
|
-
<p><a class="source-toggle" href="#"
|
134
|
-
onclick="toggleCode('M000025-source');return false;">[Source]</a></p>
|
135
|
-
<div class="method-source-code" id="M000025-source">
|
136
|
-
<pre>
|
137
|
-
<span class="ruby-comment cmt"># File lib/ankusa/naive_bayes.rb, line 12</span>
|
138
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">classifications</span>(<span class="ruby-identifier">text</span>, <span class="ruby-identifier">classnames</span>=<span class="ruby-keyword kw">nil</span>)
|
139
|
-
<span class="ruby-identifier">result</span> = <span class="ruby-identifier">log_likelihoods</span> <span class="ruby-identifier">text</span>, <span class="ruby-identifier">classnames</span>
|
140
|
-
<span class="ruby-identifier">result</span>.<span class="ruby-identifier">keys</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">k</span><span class="ruby-operator">|</span>
|
141
|
-
<span class="ruby-identifier">result</span>[<span class="ruby-identifier">k</span>] = <span class="ruby-constant">Math</span>.<span class="ruby-identifier">exp</span> <span class="ruby-identifier">result</span>[<span class="ruby-identifier">k</span>]
|
142
|
-
}
|
143
|
-
|
144
|
-
<span class="ruby-comment cmt"># normalize to get probs</span>
|
145
|
-
<span class="ruby-identifier">sum</span> = <span class="ruby-identifier">result</span>.<span class="ruby-identifier">values</span>.<span class="ruby-identifier">inject</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">x</span>,<span class="ruby-identifier">y</span><span class="ruby-operator">|</span> <span class="ruby-identifier">x</span><span class="ruby-operator">+</span><span class="ruby-identifier">y</span> }
|
146
|
-
<span class="ruby-identifier">result</span>.<span class="ruby-identifier">keys</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">k</span><span class="ruby-operator">|</span> <span class="ruby-identifier">result</span>[<span class="ruby-identifier">k</span>] = <span class="ruby-identifier">result</span>[<span class="ruby-identifier">k</span>] <span class="ruby-operator">/</span> <span class="ruby-identifier">sum</span> }
|
147
|
-
<span class="ruby-identifier">result</span>
|
148
|
-
<span class="ruby-keyword kw">end</span>
|
149
|
-
</pre>
|
150
|
-
</div>
|
151
|
-
</div>
|
152
|
-
</div>
|
153
|
-
|
154
|
-
<div id="method-M000024" class="method-detail">
|
155
|
-
<a name="M000024"></a>
|
156
|
-
|
157
|
-
<div class="method-heading">
|
158
|
-
<a href="#M000024" class="method-signature">
|
159
|
-
<span class="method-name">classify</span><span class="method-args">(text, classes=nil)</span>
|
160
|
-
</a>
|
161
|
-
</div>
|
162
|
-
|
163
|
-
<div class="method-description">
|
164
|
-
<p><a class="source-toggle" href="#"
|
165
|
-
onclick="toggleCode('M000024-source');return false;">[Source]</a></p>
|
166
|
-
<div class="method-source-code" id="M000024-source">
|
167
|
-
<pre>
|
168
|
-
<span class="ruby-comment cmt"># File lib/ankusa/naive_bayes.rb, line 6</span>
|
169
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">classify</span>(<span class="ruby-identifier">text</span>, <span class="ruby-identifier">classes</span>=<span class="ruby-keyword kw">nil</span>)
|
170
|
-
<span class="ruby-comment cmt"># return the most probable class</span>
|
171
|
-
<span class="ruby-identifier">log_likelihoods</span>(<span class="ruby-identifier">text</span>, <span class="ruby-identifier">classes</span>).<span class="ruby-identifier">sort_by</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">c</span><span class="ruby-operator">|</span> <span class="ruby-operator">-</span><span class="ruby-identifier">c</span>[<span class="ruby-value">1</span>] }.<span class="ruby-identifier">first</span>.<span class="ruby-identifier">first</span>
|
172
|
-
<span class="ruby-keyword kw">end</span>
|
173
|
-
</pre>
|
174
|
-
</div>
|
175
|
-
</div>
|
176
|
-
</div>
|
177
|
-
|
178
|
-
<div id="method-M000026" class="method-detail">
|
179
|
-
<a name="M000026"></a>
|
180
|
-
|
181
|
-
<div class="method-heading">
|
182
|
-
<a href="#M000026" class="method-signature">
|
183
|
-
<span class="method-name">log_likelihoods</span><span class="method-args">(text, classnames=nil)</span>
|
184
|
-
</a>
|
185
|
-
</div>
|
186
|
-
|
187
|
-
<div class="method-description">
|
188
|
-
<p>
|
189
|
-
Classes is an array of classes to look at
|
190
|
-
</p>
|
191
|
-
<p><a class="source-toggle" href="#"
|
192
|
-
onclick="toggleCode('M000026-source');return false;">[Source]</a></p>
|
193
|
-
<div class="method-source-code" id="M000026-source">
|
194
|
-
<pre>
|
195
|
-
<span class="ruby-comment cmt"># File lib/ankusa/naive_bayes.rb, line 25</span>
|
196
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">log_likelihoods</span>(<span class="ruby-identifier">text</span>, <span class="ruby-identifier">classnames</span>=<span class="ruby-keyword kw">nil</span>)
|
197
|
-
<span class="ruby-identifier">classnames</span> <span class="ruby-operator">||=</span> <span class="ruby-ivar">@classnames</span>
|
198
|
-
<span class="ruby-identifier">result</span> = <span class="ruby-constant">Hash</span>.<span class="ruby-identifier">new</span> <span class="ruby-value">0</span>
|
199
|
-
|
200
|
-
<span class="ruby-constant">TextHash</span>.<span class="ruby-identifier">new</span>(<span class="ruby-identifier">text</span>).<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">word</span>, <span class="ruby-identifier">count</span><span class="ruby-operator">|</span>
|
201
|
-
<span class="ruby-identifier">probs</span> = <span class="ruby-identifier">get_word_probs</span>(<span class="ruby-identifier">word</span>, <span class="ruby-identifier">classnames</span>)
|
202
|
-
<span class="ruby-identifier">classnames</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">k</span><span class="ruby-operator">|</span> <span class="ruby-identifier">result</span>[<span class="ruby-identifier">k</span>] <span class="ruby-operator">+=</span> (<span class="ruby-constant">Math</span>.<span class="ruby-identifier">log</span>(<span class="ruby-identifier">probs</span>[<span class="ruby-identifier">k</span>]) <span class="ruby-operator">*</span> <span class="ruby-identifier">count</span>) }
|
203
|
-
}
|
204
|
-
|
205
|
-
<span class="ruby-comment cmt"># add the prior and exponentiate</span>
|
206
|
-
<span class="ruby-identifier">doc_counts</span> = <span class="ruby-identifier">doc_count_totals</span>.<span class="ruby-identifier">select</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">k</span>,<span class="ruby-identifier">v</span><span class="ruby-operator">|</span> <span class="ruby-identifier">classnames</span>.<span class="ruby-identifier">include?</span> <span class="ruby-identifier">k</span> }.<span class="ruby-identifier">map</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">k</span>,<span class="ruby-identifier">v</span><span class="ruby-operator">|</span> <span class="ruby-identifier">v</span> }
|
207
|
-
<span class="ruby-identifier">doc_count_total</span> = (<span class="ruby-identifier">doc_counts</span>.<span class="ruby-identifier">inject</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">x</span>,<span class="ruby-identifier">y</span><span class="ruby-operator">|</span> <span class="ruby-identifier">x</span><span class="ruby-operator">+</span><span class="ruby-identifier">y</span> } <span class="ruby-operator">+</span> <span class="ruby-identifier">classnames</span>.<span class="ruby-identifier">length</span>).<span class="ruby-identifier">to_f</span>
|
208
|
-
<span class="ruby-identifier">classnames</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">k</span><span class="ruby-operator">|</span>
|
209
|
-
<span class="ruby-identifier">result</span>[<span class="ruby-identifier">k</span>] <span class="ruby-operator">+=</span> <span class="ruby-constant">Math</span>.<span class="ruby-identifier">log</span>((<span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">get_doc_count</span>(<span class="ruby-identifier">k</span>) <span class="ruby-operator">+</span> <span class="ruby-value">1</span>).<span class="ruby-identifier">to_f</span> <span class="ruby-operator">/</span> <span class="ruby-identifier">doc_count_total</span>)
|
210
|
-
}
|
211
|
-
|
212
|
-
<span class="ruby-identifier">result</span>
|
213
|
-
<span class="ruby-keyword kw">end</span>
|
214
|
-
</pre>
|
215
|
-
</div>
|
216
|
-
</div>
|
217
|
-
</div>
|
218
|
-
|
219
|
-
|
220
|
-
</div>
|
221
|
-
|
222
|
-
|
223
|
-
</div>
|
224
|
-
|
225
|
-
|
226
|
-
<div id="validator-badges">
|
227
|
-
<p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
|
228
|
-
</div>
|
229
|
-
|
230
|
-
</body>
|
231
|
-
</html>
|
@@ -1,275 +0,0 @@
|
|
1
|
-
<?xml version="1.0" encoding="iso-8859-1"?>
|
2
|
-
<!DOCTYPE html
|
3
|
-
PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
|
4
|
-
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
|
5
|
-
|
6
|
-
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
7
|
-
<head>
|
8
|
-
<title>Class: Ankusa::TextHash</title>
|
9
|
-
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
|
10
|
-
<meta http-equiv="Content-Script-Type" content="text/javascript" />
|
11
|
-
<link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
|
12
|
-
<script type="text/javascript">
|
13
|
-
// <![CDATA[
|
14
|
-
|
15
|
-
function popupCode( url ) {
|
16
|
-
window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
|
17
|
-
}
|
18
|
-
|
19
|
-
function toggleCode( id ) {
|
20
|
-
if ( document.getElementById )
|
21
|
-
elem = document.getElementById( id );
|
22
|
-
else if ( document.all )
|
23
|
-
elem = eval( "document.all." + id );
|
24
|
-
else
|
25
|
-
return false;
|
26
|
-
|
27
|
-
elemStyle = elem.style;
|
28
|
-
|
29
|
-
if ( elemStyle.display != "block" ) {
|
30
|
-
elemStyle.display = "block"
|
31
|
-
} else {
|
32
|
-
elemStyle.display = "none"
|
33
|
-
}
|
34
|
-
|
35
|
-
return true;
|
36
|
-
}
|
37
|
-
|
38
|
-
// Make codeblocks hidden by default
|
39
|
-
document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }</style>" )
|
40
|
-
|
41
|
-
// ]]>
|
42
|
-
</script>
|
43
|
-
|
44
|
-
</head>
|
45
|
-
<body>
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
<div id="classHeader">
|
50
|
-
<table class="header-table">
|
51
|
-
<tr class="top-aligned-row">
|
52
|
-
<td><strong>Class</strong></td>
|
53
|
-
<td class="class-name-in-header">Ankusa::TextHash</td>
|
54
|
-
</tr>
|
55
|
-
<tr class="top-aligned-row">
|
56
|
-
<td><strong>In:</strong></td>
|
57
|
-
<td>
|
58
|
-
<a href="../../files/lib/ankusa/hasher_rb.html">
|
59
|
-
lib/ankusa/hasher.rb
|
60
|
-
</a>
|
61
|
-
<br />
|
62
|
-
</td>
|
63
|
-
</tr>
|
64
|
-
|
65
|
-
<tr class="top-aligned-row">
|
66
|
-
<td><strong>Parent:</strong></td>
|
67
|
-
<td>
|
68
|
-
Hash
|
69
|
-
</td>
|
70
|
-
</tr>
|
71
|
-
</table>
|
72
|
-
</div>
|
73
|
-
<!-- banner header -->
|
74
|
-
|
75
|
-
<div id="bodyContent">
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
<div id="contextContent">
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
</div>
|
84
|
-
|
85
|
-
<div id="method-list">
|
86
|
-
<h3 class="section-bar">Methods</h3>
|
87
|
-
|
88
|
-
<div class="name-list">
|
89
|
-
<a href="#M000061">add_text</a>
|
90
|
-
<a href="#M000062">add_word</a>
|
91
|
-
<a href="#M000063">atomize</a>
|
92
|
-
<a href="#M000060">new</a>
|
93
|
-
<a href="#M000064">valid_word?</a>
|
94
|
-
</div>
|
95
|
-
</div>
|
96
|
-
|
97
|
-
</div>
|
98
|
-
|
99
|
-
|
100
|
-
<!-- if includes -->
|
101
|
-
|
102
|
-
<div id="section">
|
103
|
-
|
104
|
-
|
105
|
-
|
106
|
-
|
107
|
-
|
108
|
-
<div id="attribute-list">
|
109
|
-
<h3 class="section-bar">Attributes</h3>
|
110
|
-
|
111
|
-
<div class="name-list">
|
112
|
-
<table>
|
113
|
-
<tr class="top-aligned-row context-row">
|
114
|
-
<td class="context-item-name">word_count</td>
|
115
|
-
<td class="context-item-value"> [R] </td>
|
116
|
-
<td class="context-item-desc"></td>
|
117
|
-
</tr>
|
118
|
-
</table>
|
119
|
-
</div>
|
120
|
-
</div>
|
121
|
-
|
122
|
-
|
123
|
-
|
124
|
-
<!-- if method_list -->
|
125
|
-
<div id="methods">
|
126
|
-
<h3 class="section-bar">Public Class methods</h3>
|
127
|
-
|
128
|
-
<div id="method-M000063" class="method-detail">
|
129
|
-
<a name="M000063"></a>
|
130
|
-
|
131
|
-
<div class="method-heading">
|
132
|
-
<a href="#M000063" class="method-signature">
|
133
|
-
<span class="method-name">atomize</span><span class="method-args">(text)</span>
|
134
|
-
</a>
|
135
|
-
</div>
|
136
|
-
|
137
|
-
<div class="method-description">
|
138
|
-
<p><a class="source-toggle" href="#"
|
139
|
-
onclick="toggleCode('M000063-source');return false;">[Source]</a></p>
|
140
|
-
<div class="method-source-code" id="M000063-source">
|
141
|
-
<pre>
|
142
|
-
<span class="ruby-comment cmt"># File lib/ankusa/hasher.rb, line 33</span>
|
143
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">atomize</span>(<span class="ruby-identifier">text</span>)
|
144
|
-
<span class="ruby-identifier">text</span>.<span class="ruby-identifier">to_ascii</span>.<span class="ruby-identifier">tr</span>(<span class="ruby-value str">'-'</span>, <span class="ruby-value str">' '</span>).<span class="ruby-identifier">gsub</span>(<span class="ruby-regexp re">/[^\w\s]/</span>,<span class="ruby-value str">" "</span>).<span class="ruby-identifier">split</span>.<span class="ruby-identifier">map</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> <span class="ruby-identifier">w</span>.<span class="ruby-identifier">downcase</span> }
|
145
|
-
<span class="ruby-keyword kw">end</span>
|
146
|
-
</pre>
|
147
|
-
</div>
|
148
|
-
</div>
|
149
|
-
</div>
|
150
|
-
|
151
|
-
<div id="method-M000060" class="method-detail">
|
152
|
-
<a name="M000060"></a>
|
153
|
-
|
154
|
-
<div class="method-heading">
|
155
|
-
<a href="#M000060" class="method-signature">
|
156
|
-
<span class="method-name">new</span><span class="method-args">(text=nil)</span>
|
157
|
-
</a>
|
158
|
-
</div>
|
159
|
-
|
160
|
-
<div class="method-description">
|
161
|
-
<p><a class="source-toggle" href="#"
|
162
|
-
onclick="toggleCode('M000060-source');return false;">[Source]</a></p>
|
163
|
-
<div class="method-source-code" id="M000060-source">
|
164
|
-
<pre>
|
165
|
-
<span class="ruby-comment cmt"># File lib/ankusa/hasher.rb, line 9</span>
|
166
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">text</span>=<span class="ruby-keyword kw">nil</span>)
|
167
|
-
<span class="ruby-keyword kw">super</span> <span class="ruby-value">0</span>
|
168
|
-
<span class="ruby-ivar">@word_count</span> = <span class="ruby-value">0</span>
|
169
|
-
<span class="ruby-identifier">add_text</span>(<span class="ruby-identifier">text</span>) <span class="ruby-keyword kw">if</span> <span class="ruby-keyword kw">not</span> <span class="ruby-identifier">text</span>.<span class="ruby-identifier">nil?</span>
|
170
|
-
<span class="ruby-keyword kw">end</span>
|
171
|
-
</pre>
|
172
|
-
</div>
|
173
|
-
</div>
|
174
|
-
</div>
|
175
|
-
|
176
|
-
<div id="method-M000064" class="method-detail">
|
177
|
-
<a name="M000064"></a>
|
178
|
-
|
179
|
-
<div class="method-heading">
|
180
|
-
<a href="#M000064" class="method-signature">
|
181
|
-
<span class="method-name">valid_word?</span><span class="method-args">(word)</span>
|
182
|
-
</a>
|
183
|
-
</div>
|
184
|
-
|
185
|
-
<div class="method-description">
|
186
|
-
<p>
|
187
|
-
word should be only alphanum chars at this point
|
188
|
-
</p>
|
189
|
-
<p><a class="source-toggle" href="#"
|
190
|
-
onclick="toggleCode('M000064-source');return false;">[Source]</a></p>
|
191
|
-
<div class="method-source-code" id="M000064-source">
|
192
|
-
<pre>
|
193
|
-
<span class="ruby-comment cmt"># File lib/ankusa/hasher.rb, line 38</span>
|
194
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">valid_word?</span>(<span class="ruby-identifier">word</span>)
|
195
|
-
<span class="ruby-keyword kw">return</span> <span class="ruby-keyword kw">false</span> <span class="ruby-keyword kw">if</span> <span class="ruby-constant">Ankusa</span><span class="ruby-operator">::</span><span class="ruby-constant">STOPWORDS</span>.<span class="ruby-identifier">include?</span> <span class="ruby-identifier">word</span>
|
196
|
-
<span class="ruby-keyword kw">return</span> <span class="ruby-keyword kw">false</span> <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">word</span>.<span class="ruby-identifier">length</span> <span class="ruby-operator"><</span> <span class="ruby-value">3</span>
|
197
|
-
<span class="ruby-keyword kw">return</span> <span class="ruby-keyword kw">false</span> <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">word</span>.<span class="ruby-identifier">numeric?</span>
|
198
|
-
<span class="ruby-keyword kw">true</span>
|
199
|
-
<span class="ruby-keyword kw">end</span>
|
200
|
-
</pre>
|
201
|
-
</div>
|
202
|
-
</div>
|
203
|
-
</div>
|
204
|
-
|
205
|
-
<h3 class="section-bar">Public Instance methods</h3>
|
206
|
-
|
207
|
-
<div id="method-M000061" class="method-detail">
|
208
|
-
<a name="M000061"></a>
|
209
|
-
|
210
|
-
<div class="method-heading">
|
211
|
-
<a href="#M000061" class="method-signature">
|
212
|
-
<span class="method-name">add_text</span><span class="method-args">(text)</span>
|
213
|
-
</a>
|
214
|
-
</div>
|
215
|
-
|
216
|
-
<div class="method-description">
|
217
|
-
<p><a class="source-toggle" href="#"
|
218
|
-
onclick="toggleCode('M000061-source');return false;">[Source]</a></p>
|
219
|
-
<div class="method-source-code" id="M000061-source">
|
220
|
-
<pre>
|
221
|
-
<span class="ruby-comment cmt"># File lib/ankusa/hasher.rb, line 15</span>
|
222
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">add_text</span>(<span class="ruby-identifier">text</span>)
|
223
|
-
<span class="ruby-keyword kw">if</span> <span class="ruby-identifier">text</span>.<span class="ruby-identifier">kind_of?</span> <span class="ruby-constant">Array</span>
|
224
|
-
<span class="ruby-identifier">text</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">t</span><span class="ruby-operator">|</span> <span class="ruby-identifier">add_text</span> <span class="ruby-identifier">t</span> }
|
225
|
-
<span class="ruby-keyword kw">else</span>
|
226
|
-
<span class="ruby-comment cmt"># replace dashes with spaces, then get rid of non-word/non-space characters, </span>
|
227
|
-
<span class="ruby-comment cmt"># then split by space to get words</span>
|
228
|
-
<span class="ruby-identifier">words</span> = <span class="ruby-constant">TextHash</span>.<span class="ruby-identifier">atomize</span> <span class="ruby-identifier">text</span>
|
229
|
-
<span class="ruby-identifier">words</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">word</span><span class="ruby-operator">|</span> <span class="ruby-identifier">add_word</span>(<span class="ruby-identifier">word</span>) <span class="ruby-keyword kw">if</span> <span class="ruby-constant">TextHash</span>.<span class="ruby-identifier">valid_word?</span>(<span class="ruby-identifier">word</span>) }
|
230
|
-
<span class="ruby-keyword kw">end</span>
|
231
|
-
<span class="ruby-keyword kw">self</span>
|
232
|
-
<span class="ruby-keyword kw">end</span>
|
233
|
-
</pre>
|
234
|
-
</div>
|
235
|
-
</div>
|
236
|
-
</div>
|
237
|
-
|
238
|
-
<div id="method-M000062" class="method-detail">
|
239
|
-
<a name="M000062"></a>
|
240
|
-
|
241
|
-
<div class="method-heading">
|
242
|
-
<a href="#M000062" class="method-signature">
|
243
|
-
<span class="method-name">add_word</span><span class="method-args">(word)</span>
|
244
|
-
</a>
|
245
|
-
</div>
|
246
|
-
|
247
|
-
<div class="method-description">
|
248
|
-
<p><a class="source-toggle" href="#"
|
249
|
-
onclick="toggleCode('M000062-source');return false;">[Source]</a></p>
|
250
|
-
<div class="method-source-code" id="M000062-source">
|
251
|
-
<pre>
|
252
|
-
<span class="ruby-comment cmt"># File lib/ankusa/hasher.rb, line 27</span>
|
253
|
-
<span class="ruby-keyword kw">def</span> <span class="ruby-identifier">add_word</span>(<span class="ruby-identifier">word</span>)
|
254
|
-
<span class="ruby-ivar">@word_count</span> <span class="ruby-operator">+=</span> <span class="ruby-value">1</span>
|
255
|
-
<span class="ruby-identifier">key</span> = <span class="ruby-identifier">word</span>.<span class="ruby-identifier">stem</span>.<span class="ruby-identifier">intern</span>
|
256
|
-
<span class="ruby-identifier">store</span> <span class="ruby-identifier">key</span>, <span class="ruby-identifier">fetch</span>(<span class="ruby-identifier">key</span>, <span class="ruby-value">0</span>)<span class="ruby-operator">+</span><span class="ruby-value">1</span>
|
257
|
-
<span class="ruby-keyword kw">end</span>
|
258
|
-
</pre>
|
259
|
-
</div>
|
260
|
-
</div>
|
261
|
-
</div>
|
262
|
-
|
263
|
-
|
264
|
-
</div>
|
265
|
-
|
266
|
-
|
267
|
-
</div>
|
268
|
-
|
269
|
-
|
270
|
-
<div id="validator-badges">
|
271
|
-
<p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
|
272
|
-
</div>
|
273
|
-
|
274
|
-
</body>
|
275
|
-
</html>
|